Superintelligence Lab - Tech Lead (Agentic Search, Staff / Principal Level)
LG AI Research
| Company | LG AI Research |
| Category | Engineering |
| Location | Gangseo-gu |
| Remote | On-site (inferred) |
| Employment | Not stated |
| Level | Lead |
| Salary | Not stated by the employer |
| Posted | 23 Aug 2022 |
| Last verified | 7 Aug 2026 |
| Source | Employer ATS (greenhouse) |
Description
About the Role
우리는 사용자의 의도를 이해하고, 필요한 정보를 탐색·검증·종합하여 신뢰할 수 있는 결과를 만들어내는 agentic search system을 구축하고 있습니다. 혁신적인 retriever 학습, agentic 시스템 설계, memory/context 최적화, orchestrator RL학습, evaluation, inference efficiency까지 전체 기술 방향과 프로젝트를 이끄는 Senior Tech Lead 포지션입니다.
Staff / Principal-level MTS로서 장기적인 비전과 기술 컴포넌트를 정의하고 여러 컴포넌트 사이를 정렬하기 위한 핵심 의사결정을 내릴 수 있어야 합니다. Research outcome을 production-grade 서비스로 발전시키고, 조직의 engineering 및 research standard를 성장시켜 차세대 Tech Lead들을 육성하는 책임도 있습니다.
What You’ll Do
Set the technical vision and roadmap for end-to-end Agentic Search.
Lead execution from foundational research through production deployment.
Advance retrieval across sparse/dense/hybrid, reranking, and learning-to-retrieve systems.
Co-design model–system interfaces spanning search, memory, planning, tool use, and orchestration.
Develop RL and learning-based methods for search policies, routing, and orchestrator behavior.
Build rigorous evals for retrieval, grounding, citations, tool use, and long-horizon task completion.
Optimize quality, latency, throughput, and inference cost across the full search stack.
Provide technical leadership across Research, Engineering, Infrastructure, and Product.
Mentor senior technical talent and raise the bar for architecture, research, and execution.
You Might Thrive in This Role If You Have
Deep expertise across the full search stack, beyond dense retrieval.
Experience building agentic systems, memory systems, or learned orchestrators.
Applied RL or sequential decision-making to search, agents, or tool use.
Built end-to-end evaluation systems combining offline evals, online experiments, and production telemetry.
Scaled ML systems under demanding quality, latency, reliability, and cost constraints.
Shipped research breakthroughs as reliable, production-grade capabilities.
Led high-impact technical programs across multiple teams and disciplines.
A first-principles mindset and strong Staff / Principal-level technical judgment.
전형 절차
Application Review → Coding Test → Technical Interview (Online) → Culture Fit Interview (Onsite)
* 전형 절차는 변경될 수 있습니다. 서류 합격 시 전형 절차에 대해 별도로 안내 해 드립니다.